"""SQLite storage layer: schema init, idempotent upserts, and read queries.

Source-agnostic — the Fit REST adapter and the Takeout importer both call the
same upsert_* functions. Reads (summary/series/sessions/sleep) back the Adolf
query CLI. All writes are UPSERTs keyed on the row's natural Fit identity, so a
re-sync over an overlapping window is a no-op rather than a duplicate.
"""
import json
import os
import sqlite3
from datetime import datetime, timezone

SCHEMA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "schema.sql")


def _now_iso():
    return datetime.now(tz=timezone.utc).isoformat()


def connect(db_path):
    os.makedirs(os.path.dirname(os.path.abspath(db_path)), exist_ok=True)
    conn = sqlite3.connect(db_path)
    conn.row_factory = sqlite3.Row
    conn.execute("PRAGMA foreign_keys = ON")
    return conn


def init_db(conn):
    with open(SCHEMA_PATH) as f:
        conn.executescript(f.read())
    conn.commit()


# --- writes ---------------------------------------------------------------

def upsert_data_points(conn, rows, source="ha"):
    now = _now_iso()
    n = 0
    for r in rows:
        conn.execute(
            """
            INSERT INTO data_points
                (metric, data_type_name, start_ns, end_ns, start_time, end_time,
                 value_int, value_float, value_str, unit, data_source_id, source, ingested_at)
            VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?)
            ON CONFLICT(metric, start_ns, end_ns, data_source_id) DO UPDATE SET
                value_int=excluded.value_int,
                value_float=excluded.value_float,
                value_str=excluded.value_str,
                unit=excluded.unit,
                data_type_name=excluded.data_type_name,
                source=excluded.source,
                ingested_at=excluded.ingested_at
            """,
            (
                r["metric"], r["data_type_name"], r["start_ns"], r["end_ns"],
                r["start_time"], r["end_time"], r.get("value_int"), r.get("value_float"),
                r.get("value_str"), r.get("unit"), r.get("data_source_id", ""), source, now,
            ),
        )
        n += 1
    conn.commit()
    return n


def upsert_sleep_segments(conn, rows, source="ha"):
    now = _now_iso()
    n = 0
    for r in rows:
        conn.execute(
            """
            INSERT INTO sleep_segments
                (start_ns, end_ns, start_time, end_time, stage, stage_name,
                 data_source_id, source, ingested_at)
            VALUES (?,?,?,?,?,?,?,?,?)
            ON CONFLICT(start_ns, end_ns, data_source_id) DO UPDATE SET
                stage=excluded.stage,
                stage_name=excluded.stage_name,
                source=excluded.source,
                ingested_at=excluded.ingested_at
            """,
            (
                r["start_ns"], r["end_ns"], r["start_time"], r["end_time"],
                r["stage"], r["stage_name"], r.get("data_source_id", ""), source, now,
            ),
        )
        n += 1
    conn.commit()
    return n


def upsert_sessions(conn, rows, source="ha"):
    now = _now_iso()
    n = 0
    for r in rows:
        raw = r.get("raw_json")
        if raw is not None and not isinstance(raw, str):
            raw = json.dumps(raw)
        conn.execute(
            """
            INSERT INTO sessions
                (id, name, description, activity_type, activity_name, start_ns, end_ns,
                 start_time, end_time, modified_ns, application, source, raw_json, ingested_at)
            VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?)
            ON CONFLICT(id) DO UPDATE SET
                name=excluded.name,
                description=excluded.description,
                activity_type=excluded.activity_type,
                activity_name=excluded.activity_name,
                start_ns=excluded.start_ns,
                end_ns=excluded.end_ns,
                start_time=excluded.start_time,
                end_time=excluded.end_time,
                modified_ns=excluded.modified_ns,
                application=excluded.application,
                source=excluded.source,
                raw_json=excluded.raw_json,
                ingested_at=excluded.ingested_at
            """,
            (
                r["id"], r.get("name"), r.get("description"), r.get("activity_type"),
                r.get("activity_name"), r["start_ns"], r["end_ns"], r["start_time"],
                r["end_time"], r.get("modified_ns"), r.get("application"), source, raw, now,
            ),
        )
        n += 1
    conn.commit()
    return n


# --- sync cursor & run audit ---------------------------------------------

def get_last_synced_ns(conn, stream_key):
    row = conn.execute(
        "SELECT last_synced_ns FROM sync_state WHERE stream_key=?", (stream_key,)
    ).fetchone()
    return row["last_synced_ns"] if row else 0


def set_sync_state(conn, stream_key, last_synced_ns, status="ok", error=None):
    conn.execute(
        """
        INSERT INTO sync_state (stream_key, last_synced_ns, last_run_at, last_status, last_error)
        VALUES (?,?,?,?,?)
        ON CONFLICT(stream_key) DO UPDATE SET
            last_synced_ns=MAX(sync_state.last_synced_ns, excluded.last_synced_ns),
            last_run_at=excluded.last_run_at,
            last_status=excluded.last_status,
            last_error=excluded.last_error
        """,
        (stream_key, last_synced_ns, _now_iso(), status, error),
    )
    conn.commit()


def start_run(conn):
    cur = conn.execute(
        "INSERT INTO ingest_runs (started_at, status) VALUES (?, 'running')", (_now_iso(),)
    )
    conn.commit()
    return cur.lastrowid


def finish_run(conn, run_id, status, points=0, sessions=0, segments=0, error=None):
    conn.execute(
        """UPDATE ingest_runs SET finished_at=?, status=?, points_upserted=?,
           sessions_upserted=?, segments_upserted=?, error=? WHERE id=?""",
        (_now_iso(), status, points, sessions, segments, error, run_id),
    )
    conn.commit()


# --- reads (Adolf query tool) --------------------------------------------

def daily_metric(conn, metric, days=14):
    return [dict(r) for r in conn.execute(
        """SELECT date(start_time) AS day,
                  SUM(COALESCE(value_int, value_float)) AS total,
                  MAX(unit) AS unit
           FROM data_points WHERE metric=?
             AND start_time >= datetime('now', ?)
           GROUP BY day ORDER BY day DESC""",
        (metric, f"-{int(days)} days"),
    ).fetchall()]


def latest_metric(conn, metric, limit=20):
    return [dict(r) for r in conn.execute(
        """SELECT start_time, end_time, value_int, value_float, unit
           FROM data_points WHERE metric=? ORDER BY start_ns DESC LIMIT ?""",
        (metric, int(limit)),
    ).fetchall()]


def recent_sessions(conn, days=30, limit=50):
    return [dict(r) for r in conn.execute(
        """SELECT id, name, activity_type, activity_name, start_time, end_time,
                  (end_ns - start_ns)/60000000000.0 AS duration_min
           FROM sessions WHERE start_time >= datetime('now', ?)
           ORDER BY start_ns DESC LIMIT ?""",
        (f"-{int(days)} days", int(limit)),
    ).fetchall()]


def sleep_by_night(conn, days=14):
    """Total minutes per stage grouped by the calendar day the sleep segment ends
    (a night that crosses midnight is attributed to the wake day)."""
    return [dict(r) for r in conn.execute(
        """SELECT date(end_time) AS night, stage_name,
                  SUM((end_ns - start_ns)/60000000000.0) AS minutes
           FROM sleep_segments WHERE end_time >= datetime('now', ?)
           GROUP BY night, stage_name ORDER BY night DESC""",
        (f"-{int(days)} days",),
    ).fetchall()]


def summary(conn):
    """Compact health snapshot for Adolf: row counts, coverage, freshness."""
    out = {}
    for name, q in (
        ("data_points", "SELECT COUNT(*) c FROM data_points"),
        ("sessions", "SELECT COUNT(*) c FROM sessions"),
        ("sleep_segments", "SELECT COUNT(*) c FROM sleep_segments"),
    ):
        out[name] = conn.execute(q).fetchone()["c"]
    out["metrics"] = [r["metric"] for r in conn.execute(
        "SELECT DISTINCT metric FROM data_points ORDER BY metric").fetchall()]
    span = conn.execute(
        "SELECT MIN(start_time) a, MAX(start_time) b FROM data_points").fetchone()
    out["coverage"] = {"earliest": span["a"], "latest": span["b"]}
    out["sync_state"] = [dict(r) for r in conn.execute(
        "SELECT stream_key, last_run_at, last_status FROM sync_state").fetchall()]
    last = conn.execute(
        "SELECT started_at, finished_at, status, points_upserted FROM ingest_runs "
        "ORDER BY id DESC LIMIT 1").fetchone()
    out["last_run"] = dict(last) if last else None
    return out